-
1.发明公开
公开(公告)号：EP4310732A2
公开(公告)日：2024-01-24
申请号：EP23206103.6
申请日：2019-10-18
发明人： BELFIORE, Jean-Claude , PASCHOS, Georgios , TSILIMANTOS, Dimitrios , DESTOUNIS, Apostolos , VASSILARAS, Spyridon , COSTANTINI, Marina , LIAKOPOULOS, Nikolaos , NGUYEN, Van, Minh , DEBBAH, Merouane
IPC分类号： G06N3/063
摘要： A data processing system having a neural network architecture for receiving a binary network input and, in dependence on the binary network input, propagating signals via a plurality of processing nodes, in accordance with respective binary weights, to form a network output, the data processing system being configured to train a node by implementing an error correcting function to identify a set of binary weights which minimize, for a given input to the node, any error between an output of the node when formed in accordance with current binary weights of the node and a preferred output from the node and to update the binary weights of the node to be the identified weights. This training is performed without storing and/or using any higher arithmetic precision weights or other components.
-
公开(公告)号：EP3676993A1
公开(公告)日：2020-07-08
申请号：EP18800367.7
申请日：2018-10-15
-
3.发明公开
公开(公告)号：EP4310732A3
公开(公告)日：2024-04-03
申请号：EP23206103.6
申请日：2019-10-18
发明人： BELFIORE, Jean-Claude , PASCHOS, Georgios , TSILIMANTOS, Dimitrios , DESTOUNIS, Apostolos , VASSILARAS, Spyridon , COSTANTINI, Marina , LIAKOPOULOS, Nikolaos , NGUYEN, Van, Minh , DEBBAH, Merouane
摘要： A data processing system having a neural network architecture for receiving a binary network input and, in dependence on the binary network input, propagating signals via a plurality of processing nodes, in accordance with respective binary weights, to form a network output, the data processing system being configured to train a node by implementing an error correcting function to identify a set of binary weights which minimize, for a given input to the node, any error between an output of the node when formed in accordance with current binary weights of the node and a preferred output from the node and to update the binary weights of the node to be the identified weights. This training is performed without storing and/or using any higher arithmetic precision weights or other components.
-
4.发明公开
公开(公告)号：EP4035273A1
公开(公告)日：2022-08-03
申请号：EP19790200.0
申请日：2019-10-18
-
-
-
搜索结果
4 条记录 (耗时 0.009 秒)
